Book Image

Machine Learning Security Principles

By : John Paul Mueller
Book Image

Machine Learning Security Principles

By: John Paul Mueller

Overview of this book

Businesses are leveraging the power of AI to make undertakings that used to be complicated and pricy much easier, faster, and cheaper. The first part of this book will explore these processes in more depth, which will help you in understanding the role security plays in machine learning. As you progress to the second part, you’ll learn more about the environments where ML is commonly used and dive into the security threats that plague them using code, graphics, and real-world references. The next part of the book will guide you through the process of detecting hacker behaviors in the modern computing environment, where fraud takes many forms in ML, from gaining sales through fake reviews to destroying an adversary’s reputation. Once you’ve understood hacker goals and detection techniques, you’ll learn about the ramifications of deep fakes, followed by mitigation strategies. This book also takes you through best practices for embracing ethical data sourcing, which reduces the security risk associated with data. You’ll see how the simple act of removing personally identifiable information (PII) from a dataset lowers the risk of social engineering attacks. By the end of this machine learning book, you'll have an increased awareness of the various attacks and the techniques to secure your ML systems effectively.
Table of Contents (19 chapters)
Part 1 – Securing a Machine Learning System
Part 2 – Creating a Secure System Using ML
Part 3 – Protecting against ML-Driven Attacks
Part 4 – Performing ML Tasks in an Ethical Manner

Addressing fairness concerns

The first step in solving a problem is to know the problem exists. Right now, most people who create models have no idea that a problem exists. This lack of knowledge and understanding is the reason that models such as those used in the Correctional Offender Management Profiling for Alternative Sanctions (COMPAS) software fail on a grand scale. If the software had been vetted with some type of fairness indicator, then there is a higher likelihood that it would have produced a fair result. The following sections look at methods of working with fairness indicators that make it possible to produce models that output a fairer result.

Is a completely fair result possible?

It isn’t actually possible to create a completely fair result today. There is a paradox involved. Either a model can treat groups fairly or it can treat individuals fairly. You can find a wealth of white papers on the topic, such as On the Apparent Conflict Between Individual and...